Information Extraction Module Research Articles

DiffMAR: A Generalized Diffusion Model for Metal Artifact Reduction in CT Images.

X-ray imaging frequently introduces varying degrees of metal artifacts to computed tomography (CT) images when metal implants are present. For the metal artifact reduction (MAR) task, existing end-to-end methods often exhibit limited generalization capabilities. While methods based on multiple iterations often suffer from accumulative error, resulting in lower-quality restoration outcomes. In this work, we innovatively present a generalized diffusion model for Metal Artifact Reduction (DiffMAR). The proposed method utilizes a linear degradation process to simulate the physical phenomenon of metal artifact formation in CT images and directly learn an iterative restoration process from paired CT images in the reverse process. During the reverse process of DiffMAR, a Time-Latent Adjustment (TLA) module is designed to adjust time embedding at the latent level, thereby minimizing the accumulative error during iterative restoration. We also designed a structure information extraction (SIE) module to utilize linear interpolation data in the image domain, guiding the generation of anatomical structures during the iterative restoring. This leads to more accurate and robust shadow-free image generation. Comprehensive analysis, including both synthesized data and clinical evidence, confirms that our proposed method surpasses the current state-of-the-art (SOTA) MAR methods in terms of both image generation quality and generalization.

Extracting terrain elevation information in front of the vehicle based on vehicle-mounted LiDAR in dynamic environments

Abstract Point cloud maps constructed using 3D LiDAR, are widely used for robot navigation and localization. Few studies have utilized point cloud maps to extract terrain elevationinformation in front of a vehicle, which can be used as active suspension inputs to reduce vehicle bumps. In addition, the trajectories of dynamic objects in point cloud maps and global navigation satellite system (GNSS) data loss can affect the extraction of elevation information. To solve these problems, this paper proposes a framework for extracting terrain elevation information in front of the vehicle based on vehicle-mounted LiDAR in dynamic environments. The framework consists of two modules: point cloud map construction and vehicle front terrain elevation information extraction. In the point cloud map construction module, a system for simultaneous localization and mapping (SLAM) is proposed, which is capable of building point cloud maps without GNSS. Furthermore, a dynamic descriptor-based dynamic object filtering algorithm is proposed which is applied to SLAM. Therefore, the SLAM system overcomes the influence of dynamic objects on vehicle position and attitude estimation, and there are no trajectories of dynamic objects in the point cloud maps built by the system. In the vehicle front terrain elevation information extraction module, the unscented Kalman filter is utilized to predict the vehicle position at the next moment. Based on the geometric features of the tire-ground contact area, the terrain elevation information of the tire contact area at the predicted position on the point cloud map is extracted. Experiments show that the algorithm in this paper overcomes the effect of dynamic objects and builds a vehicle point cloud map without dynamic objects under GNSS data loss, which improves the accuracy of the extraction of terrain elevation information in front of the vehicle.

Semi‐supervised contextual cognitive augmentation‐based cross‐teaching network for multiclass medical image segmentation

AbstractThe application of medical image segmentation technology enables accurate localization of human tissues, providing doctors with a reliable foundation for diagnosis. While deep learning methods have proven effective in this task, most current approaches rely on a single prediction framework, which overlooks Edge semantic features and results in flawed texture features. Moreover, existing supervised methods face challenges due to limited availability of high‐quality annotations in the field of medical imaging. In this article, a Semi‐supervised Contextual Cognitive Augmentation‐based Cross‐teaching Network is proposed. A Contextual Cognitive Enhancement Module is introduced consisting of two components: data augmentation and information extraction. The data augmentation component provides multi‐level data distribution by incorporating diverse perturbation strategies such as Discrete Cosine Transform and Gaussian noise. The information extraction component employs the Comprehensive Information Extraction module, which consists of Global Perception Information Extraction module and Multi‐channel Information Extraction module to extract perceptual information from images and enhance interaction between image channels, respectively. Additionally, a cross‐teaching strategy is adopted and a hybrid loss function is utilized to encourage knowledge sharing among the networks, leveraging the advantages of dual networks for improved performance. Experimental results demonstrate significant enhancements in multiclass medical image segmentation compared to several state‐of‐the‐art single‐framework networks.

Finding meaningful paths in heterogeneous graphs with PathWays

Graphs, and notably RDF graphs, are a prominent way of sharing data. As data usage democratizes, users need help figuring out the useful content of a graph dataset. In particular, journalists with whom we collaborate are interested in identifying, in a graph, the connections between entities, e.g., people, organizations, emails, etc. We present a novel method for exploring data graphs through their data paths connecting Named Entities (NEs, in short); each data path leads to a tabular-looking set of results. NEs are extracted from the data through dedicated Information Extraction modules. Our method builds upon the pre-existing ConnectionLens platform and follow-up work in the Abstra project, which builds simple, visual ER-style summaries of semi-structured data. The contribution of the present work, and its novelty, is twofold. First, we propose a novel analysis of entity-to-entity paths contained in datasets of any nature, and propose a new method for ranking paths, leveraging a novel Information Extraction (IE) module we built on top of ChatGPT. Second, we present an efficient approach to enumerate and compute NE paths, based on an algorithm which automatically recommends sub-paths to materialize, and rewrites the path queries using these subpaths. Our experiments demonstrate the interest of NE paths and the efficiency of our method for computing and ranking them.

SEY‐Net: Semantic edge Y‐shaped network for pancreas segmentation

AbstractPancreas segmentation has great significance in computer‐aided diagnosis of pancreatic diseases. The small size of the pancreas, high variability in shape, and blurred edges make the task of pancreas segmentation challenging. A new model called SEY‐Net is proposed to solve the above problems, which is a one‐stage model with multi‐inputs. SEY‐Net is composed of three main components. Firstly, the edge information extraction (EIE) module is designed to improve the segmentation accuracy of the pancreas boundary. Then, the SE_ResNet50 is selected as the encoder's backbone to fit the size of the pancreas. Finally, the dual cross‐attention is integrated into the skip connection to better focus on the variable shape of the pancreas. The experimental results shows that the proposed method has better performance and outperforms the other existing state‐of‐the‐art pancreas segmentation methods.

MFLD: lightweight object detection with multi-receptive field and long-range dependency in remote sensing images

PurposeBased on the strong feature representation ability of the convolutional neural network (CNN), generous object detection methods in remote sensing (RS) have been proposed one after another. However, due to the large variation in scale and the omission of relevant relationships between objects, there are still great challenges for object detection in RS. Most object detection methods fail to take the difficulties of detecting small and medium-sized objects and global context into account. Moreover, inference time and lightness are also major pain points in the field of RS.Design/methodology/approachTo alleviate the aforementioned problems, this study proposes a novel method for object detection in RS, which is called lightweight object detection with a multi-receptive field and long-range dependency in RS images (MFLD). The multi-receptive field extraction (MRFE) and long-range dependency information extraction (LDIE) modules are put forward.FindingsTo concentrate on the variability of objects in RS, MRFE effectively expands the receptive field by a combination of atrous separable convolutions with different dilated rates. Considering the shortcomings of CNN in extracting global information, LDIE is designed to capture the relationships between objects. Extensive experiments over public datasets in RS images demonstrate that our MFLD method surpasses the state-of-the-art methods. Most of all, on the NWPU VHR-10 dataset, our MFLD method achieves 94.6% mean average precision with 4.08 M model volume.Originality/valueThis paper proposed a method called lightweight object detection with multi-receptive field and long-range dependency in RS images.

Style Optimization Networks for real-time semantic segmentation of rainy and foggy weather

Semantic segmentation is an essential task in the field of computer vision. Existing semantic segmentation models can achieve good results under good weather and lighting conditions. However, when the external environment changes, the effectiveness of these models are seriously affected. Therefore, we focus on the task of semantic segmentation in rainy and foggy weather. Fog is a common phenomenon in rainy weather conditions and has a negative impact on image visibility. Besides, to make the algorithm satisfy the application requirements of mobile devices, the computational cost and the real-time requirement of the model have become one of the major points of our research. In this paper, we propose a novel Style Optimization Network (SONet) architecture, containing a Style Optimization Module (SOM) that can dynamically learn style information, and a Key information Extraction Module (KEM) that extracts important spatial and contextual information. This can improve the learning ability and robustness of the model for rainy and foggy conditions. Meanwhile, we achieve real-time performance by using lightweight modules and a backbone network with low computational complexity. To validate the effectiveness of our SONet, we synthesized CityScapes dataset for rainy and foggy weather and evaluated the accuracy and complexity of our model. Our model achieves a segmentation accuracy of 75.29% MIoU and 83.62% MPA on a NVIDIA TITAN Xp GPU. Several comparative experiments have shown that our SONet can achieve good performance in semantic segmentation tasks under rainy and foggy weather, and due to the lightweight design of the model we have a good advantage in both accuracy and model complexity.

Multimodal graph learning with framelet-based stochastic configuration networks for emotion recognition in conversation

The multimodal emotion recognition in conversation (ERC) task presents significant challenges due to the complexity of relationships and the difficulty in achieving semantic fusion across various modalities. Graph learning, recognized for its capability to capture intricate data relations, has been suggested as a solution for ERC. However, existing graph-based ERC models often fail to address the fundamental limitations of graph learning, such as assuming pairwise interactions and neglecting high-frequency signals in semantically-poor modalities, which leads to an over-reliance on text. While these issues might be negligible in other applications, they are crucial for the success of ERC. In this paper, we propose a novel framework for ERC, namely multimodal graph learning with framelet-based stochastic configuration networks (i.e., Frame-SCN). Specifically, framelet-based stochastic configuration networks, which employ 2D directional Haar framelets to extract both low- and high-pass components, are introduced to learn the unified semantic embeddings from multimodal data, mitigating prediction biases caused by an excessive reliance on text without introducing an unnecessarily large number of parameters. Also, we develop a modality-aware information extraction module that is able to extract both general and sensitive information in a multimodal semantic space, alleviating potential noise issues. Extensive experiment results demonstrate that our proposed Frame-SCN outperforms many state-of-the-art approaches on two widely used multimodal ERC datasets.

Multi-level interactive fusion network based on adversarial learning for fusion classification of hyperspectral and LiDAR data

With the growing awareness of the limitations of unimodal data, research on joint classification using multimodal remote sensing data has garnered increasing attention. However, existing methods still have certain deficiencies in dealing with feature extraction and feature fusion of multimodal remote sensing data. In order to obtain more accurate classification results, it is crucial to fully exploit and utilize the complementary information in multimodal remote sensing data. In this paper, a multi-level interactive fusion network based on adversarial learning (MLIF-AL) is proposed for hyperspectral image (HSI) and light detection and ranging (LiDAR) data fusion classification. First, the feature extraction part based on generative adversarial network (GAN) utilizes adversarial training between the generator and the discriminator to guide the network to learn more discriminative and distinguished feature representations. Meanwhile, a cross-modal interactive information extraction (CMIIE) module is also designed for the generator encoding part to promote the interaction between multimodal data from a global perspective and realize the full utilization of multimodal complementary information. In addition, in the multi-level feature fusion classification (MLFFC) part, the complementarities between the features learned by the neural networks at each layer are comprehensively utilized to obtain higher-level multimodal fusion semantic information. Finally, the adversarial loss and classification loss are combined for network training. Extensive experiments on three commonly used HSI and LiDAR datasets and comparisons with state-of-the-art methods demonstrate the effectiveness and superiority of the model.

An Effective and Lightweight Full-Scale Target Detection Network for UAV Images Based on Deformable Convolutions and Multi-Scale Contextual Feature Optimization

Currently, target detection on unmanned aerial vehicle (UAV) images is a research hotspot. Due to the significant scale variability of targets and the interference of complex backgrounds, current target detection models face challenges when applied to UAV images. To address these issues, we designed an effective and lightweight full-scale target detection network, FSTD-Net. The design of FSTD-Net is based on three principal aspects. Firstly, to optimize the extracted target features at different scales while minimizing background noise and sparse feature representations, a multi-scale contextual information extraction module (MSCIEM) is developed. The multi-scale information extraction module (MSIEM) in MSCIEM can better capture multi-scale features, and the contextual information extraction module (CIEM) in MSCIEM is designed to capture long-range contextual information. Secondly, to better adapt to various target shapes at different scales in UAV images, we propose the feature extraction module fitting different shapes (FEMFDS), based on deformable convolutions. Finally, considering low-level features contain rich details, a low-level feature enhancement branch (LLFEB) is designed. The experiments demonstrate that, compared to the second-best model, the proposed FSTD-Net achieves improvements of 3.8%, 2.4%, and 2.0% in AP50, AP, and AP75 on the VisDrone2019, respectively. Additionally, FSTD-Net achieves enhancements of 3.4%, 1.7%, and 1% on the UAVDT dataset. Our proposed FSTD-Net has better detection performance compared to state-of-the-art detection models. The experimental results indicate the effectiveness of the FSTD-Net for target detection in UAV images.

DyHDGE: Dynamic heterogeneous transaction graph embedding for safety-centric fraud detection in financial scenarios

Dynamic graph fraud detection aims to distinguish fraudulent entities that deviate significantly from most benign entities within an ever-changing graph network. However, when dealing with different financial fraud scenarios, existing methods face challenges, resulting in difficulty in effectively ensuring financial security. In fraud scenarios, transaction data are generated in real time, in which a strong temporal relationship between multiple fraudulent transactions is observed. Traditional dynamic graph models struggle to effectively balance the temporal features of nodes and spatial structural features, failing to handle different types of nodes in the graph network. In this study, to extract the temporal and structural information, we proposed a dynamic heterogeneous transaction graph embedding (DyHDGE) network based on a dynamic heterogeneous transaction graph, considering both temporal and structural information while incorporating heterogeneous data. To separately extract temporal relationships between transactions and spatial structural relationships between nodes, we used a heterogeneous temporal graph representation learning module and a temporal graph structure information extraction module. Additionally, we designed two loss functions to optimize node feature representations. Extensive experiments demonstrated that the proposed DyHDGE significantly outperformed previous state-of-the-art methods on two simulated datasets of financial fraud scenarios. This capability contributes to enhancing security in financial consumption scenarios.

Explainable semantic wireless anomaly characterization for digital twins

The shift towards software-centric network infrastructures is driven by the increasing need for networks to be responsive, flexible, and scalable in the face of an expanding set of connected devices. The digital twin (DT) approach, mirroring physical entities in a digital format, has emerged as a key enabler of network reliability and availability. Incorporating artificial intelligence (AI) into DTs enhances the resilience of networks by providing in-depth analysis and increasingly automated mitigation strategies against operational disruptions. In this work, we propose a new AI-based information extraction module that is part of the DT Monitoring component able to process RSS data, extract and characterize abrupt anomalies. The output of this component is used to maintain an anomaly history in the Link Abstraction within the DT and subsequently inform possible automatic mitigation actions. We design the AI-based information extraction module to identify and characterize three types of RSS based anomalies. Our extensive performance analysis on 10 versions of the “You Only Look Once” architecture reveals that YOLOv8n produces a good tradeoff between performance and computational complexity. We show that our approach performs on par with the state of the art for anomaly detection, while enabling anomaly characterization by location, duration, and severity. By employing two SotA explainability algorithms, we also provide insights into the important regions of the input that trigger the selected model’s classification and characterization decisions.

Semantic-Aware Fusion Network Based on Super-Resolution.

The aim of infrared and visible image fusion is to generate a fused image that not only contains salient targets and rich texture details, but also facilitates high-level vision tasks. However, due to the hardware limitations of digital cameras and other devices, there are more low-resolution images in the existing datasets, and low-resolution images are often accompanied by the problem of losing details and structural information. At the same time, existing fusion algorithms focus too much on the visual quality of the fused images, while ignoring the requirements of high-level vision tasks. To address the above challenges, in this paper, we skillfully unite the super-resolution network, fusion network and segmentation network, and propose a super-resolution-based semantic-aware fusion network. First, we design a super-resolution network based on a multi-branch hybrid attention module (MHAM), which aims to enhance the quality and details of the source image, enabling the fusion network to integrate the features of the source image more accurately. Then, a comprehensive information extraction module (STDC) is designed in the fusion network to enhance the network's ability to extract finer-grained complementary information from the source image. Finally, the fusion network and segmentation network are jointly trained to utilize semantic loss to guide the semantic information back to the fusion network, which effectively improves the performance of the fused images on high-level vision tasks. Extensive experiments show that our method is more effective than other state-of-the-art image fusion methods. In particular, our fused images not only have excellent visual perception effects, but also help to improve the performance of high-level vision tasks.

FF-HPINet: A Flipped Feature and Hierarchical Position Information Extraction Network for Lane Detection.

Effective lane detection technology plays an important role in the current autonomous driving system. Although deep learning models, with their intricate network designs, have proven highly capable of detecting lanes, there persist key areas requiring attention. Firstly, the symmetry inherent in visuals captured by forward-facing automotive cameras is an underexploited resource. Secondly, the vast potential of position information remains untapped, which can undermine detection precision. In response to these challenges, we propose FF-HPINet, a novel approach for lane detection. We introduce the Flipped Feature Extraction module, which models pixel pairwise relationships between the flipped feature and the original feature. This module allows us to capture symmetrical features and obtain high-level semantic feature maps from different receptive fields. Additionally, we design the Hierarchical Position Information Extraction module to meticulously mine the position information of the lanes, vastly improving target identification accuracy. Furthermore, the Deformable Context Extraction module is proposed to distill vital foreground elements and contextual nuances from the surrounding environment, yielding focused and contextually apt feature representations. Our approach achieves excellent performance with the F1 score of 97.00% on the TuSimple dataset and 76.84% on the CULane dataset.

Multidimensional information fusion and analysis of ultraviolet absorption spectroscopy: Simultaneous detection method for copper and zinc ion concentrations in seawater

Heavy metal pollution poses a significant threat to marine ecological environments and serves as a crucial indicator for seawater quality assessment. The enrichment of heavy metals severely impacts marine ecosystem health and poses threats to human food safety, underscoring the critical importance of monitoring heavy metal levels in marine waters. In this paper, UV absorption spectroscopy was used to collect the spectra of seawater containing different concentrations of Cu and Zn ions, which overcomes the problems of traditional methods that require extensive pre-treatment and lossy samples. To address the characteristics of the data, the Savitzky-Golay (SG) filtering algorithm is used for preprocessing. The acquired spectra are then subjected to further data analysis using the proposed multidimensional information fusion method called SpectraNet Fusion Algorithm (SFA) for UV absorption spectroscopy. The local feature information extraction module and the whole domain information feature extraction module were respectively used to predict the regression of the data in parallel two-channel, and the output results were integrated to form a new feature map, which was further processed by the feature information fusion module, and finally output the prediction results corresponding to the spectra to realize the accurate detection of Cu and Zn heavy metal ions in seawater. The coefficient of determination (R2) of the model training set established by this method reaches 98.00 %, the root mean square error (RMSE) reaches 0.0389, and the mean absolute error (MAE) reaches 0.0243, combined with the experimental design, the detection range was 5 μg·L−1 to 90 μg·L−1,which realizes simultaneous and high-precision prediction of Cu and Zn heavy metal ions in seawater.

Critical Information Mining Network: Identifying Crop Diseases in Noisy Environments

When agricultural experts explore the use of artificial intelligence technology to identify and detect crop diseases, they mainly focus on the research of a stable environment, but ignore the problem of noise in the process of image acquisition in real situations. To solve this problem, we propose an innovative solution called the Critical Information Mining Network (CIMNet). Compared with traditional models, CIMNet has higher recognition accuracy and wider application scenarios. The network has a good effect on crop disease recognition under noisy environments, and can effectively deal with the interference of noise to the recognition effect in actual farmland scenes. Consider that the shape of the leaves can be symmetrical or asymmetrical.First, we introduce the Non-Local Attention Module (Non-Local), which uses a unique self-attention mechanism to fully capture the context information of the image. The module overcomes the limitation of traditional convolutional neural networks that only rely on local features and ignore global features. Global features are particularly important when the image is disturbed by noise. Non-Local improves a more comprehensive visual understanding of crop disease recognition. Secondly, we have innovatively designed a Multi-scale Critical Information Fusion Module (MSCM). The module uses the Key Information Extraction Module (KIB) to dig into the shallow key features in the network deeply. The shallow key features strengthen the feature perception of the model to the noise image through texture and contour information, and then the shallow key features and deep features are fused to enrich the original deep feature information of the network. Finally, we conducted experiments on two public datasets, and the results showed that the accuracy of our model in crop disease identification under a noisy environment was significantly improved. At the same time, our model also showed excellent performance under stable conditions. The results of this study provide favorable support for the improvement of crop production efficiency.

Hyperspectral Image Classification Based on Two-Branch Multiscale Spatial Spectral Feature Fusion with Self-Attention Mechanisms

In recent years, the use of deep neural network in effective network feature extraction and the design of efficient and high-precision hyperspectral image classification algorithms has gradually become a research hotspot for scholars. However, due to the difficulty of obtaining hyperspectral images and the high cost of annotation, the training samples are very limited. In order to cope with the small sample problem, researchers often deepen the network model and use the attention mechanism to extract features; however, as the network model continues to deepen, the gradient disappears, the feature extraction ability is insufficient, and the computational cost is high. Therefore, how to make full use of the spectral and spatial information in limited samples has gradually become a difficult problem. In order to cope with such problems, this paper proposes two-branch multiscale spatial–spectral feature aggregation with a self-attention mechanism for a hyperspectral image classification model (FHDANet); the model constructs a dense two-branch pyramid structure, which can achieve the high efficiency extraction of joint spatial–spectral feature information and spectral feature information, reduce feature loss to a large extent, and strengthen the model’s ability to extract contextual information. A channel–space attention module, ECBAM, is proposed, which greatly improves the extraction ability of the model for salient features, and a spatial information extraction module based on the deep feature fusion strategy HLDFF is proposed, which fully strengthens feature reusability and mitigates the feature loss problem brought about by the deepening of the model. Compared with five hyperspectral image classification algorithms, SVM, SSRN, A2S2K-ResNet, HyBridSN, SSDGL, RSSGL and LANet, this method significantly improves the classification performance on four representative datasets. Experiments have demonstrated that FHDANet can better extract and utilise the spatial and spectral information in hyperspectral images with excellent classification performance under small sample conditions.

MFEFNet: A Multi-Scale Feature Information Extraction and Fusion Network for Multi-Scale Object Detection in UAV Aerial Images

Unmanned aerial vehicles (UAVs) are now widely used in many fields. Due to the randomness of UAV flight height and shooting angle, UAV images usually have the following characteristics: many small objects, large changes in object scale, and complex background. Therefore, object detection in UAV aerial images is a very challenging task. To address the challenges posed by these characteristics, this paper proposes a novel UAV image object detection method based on global feature aggregation and context feature extraction named the multi-scale feature information extraction and fusion network (MFEFNet). Specifically, first of all, to extract the feature information of objects more effectively from complex backgrounds, we propose an efficient spatial information extraction (SIEM) module, which combines residual connection to build long-distance feature dependencies and effectively extracts the most useful feature information by building contextual feature relations around objects. Secondly, to improve the feature fusion efficiency and reduce the burden brought by redundant feature fusion networks, we propose a global aggregation progressive feature fusion network (GAFN). This network adopts a three-level adaptive feature fusion method, which can adaptively fuse multi-scale features according to the importance of different feature layers and reduce unnecessary intermediate redundant features by utilizing the adaptive feature fusion module (AFFM). Furthermore, we use the MPDIoU loss function as the bounding-box regression loss function, which not only enhances model robustness to noise but also simplifies the calculation process and improves the final detection efficiency. Finally, the proposed MFEFNet was tested on VisDrone and UAVDT datasets, and the mAP0.5 value increased by 2.7% and 2.2%, respectively.

Brain tumor segmentation in MRI with multi-modality spatial information enhancement and boundary shape correction

Brain tumor segmentation is currently of a priori guiding significance in medical research and clinical diagnosis. Brain tumor segmentation techniques can accurately partition different tumor areas on multi-modality images captured by magnetic resonance imaging (MRI). Due to the unpredictable pathological process of brain tumor generation and growth, brain tumor images often show irregular shapes and uneven internal gray levels. Existing neural network-based segmentation methods with an encoding/decoding structure can perform image segmentation to some extent. However, they ignore issues such as differences in multi-modality information, loss of spatial information, and under-utilization of boundary information, thereby limiting the further improvement of segmentation accuracy. This paper proposes a multimodal spatial information enhancement and boundary shape correction method consisting of a modality information extraction (MIE) module, a spatial information enhancement (SIE) module, and a boundary shape correction (BSC) module. The above three modules act on the input, backbone, and loss functions of deep convolutional networks (DCNN), respectively, and compose an end-to-end 3D brain tumor segmentation model. The three proposed modules can solve the low utilization rate of effective modality information, the insufficient spatial information acquisition ability, and the improper segmentation of key boundary positions can be solved. The proposed method was validated on BraTS2017, 2018, and 2019 datasets. Comparative experimental results confirmed the effectiveness and superiority of the proposed method over state-of-the-art segmentation methods.

A study of extractive summarization of long documents incorporating local topic and hierarchical information

In recent years, the transformer-based language models have achieved remarkable success in the field of extractive text summarization. However, there are still some limitations in this kind of research. First, the transformer language model usually regards the text as a linear sequence, ignoring the inherent hierarchical structure information of the text. Second, for long text data, traditional extractive models often focus on global topic information, which poses challenges in how they capturing and integrating local contextual information within topic segments. To address these issues, we propose a long text extractive summarization model that employs a local topic information extraction module and a text hierarchical extraction module to capture the local topic information and document's hierarchical structure information of the original text. Our approach enhances the ability to determine whether a sentence belongs to the summary. In this experiment, ROUGE score is used as the experimental evaluation index, and evaluates the model on three large public datasets. Through experimental validation, the model demonstrates superior performance in terms of ROUGE-1, ROUGE-2, and ROUGE-L scores compared to current mainstream summarization models, affirming the effectiveness of incorporating local topic information and document hierarchical structure into the model.